{"id":"https://openalex.org/W3003448205","doi":"https://doi.org/10.48550/arxiv.2002.00122","title":"Multi-channel Acoustic Modeling using Mixed Bitrate OPUS Compression","display_name":"Multi-channel Acoustic Modeling using Mixed Bitrate OPUS Compression","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3003448205","doi":"https://doi.org/10.48550/arxiv.2002.00122","mag":"3003448205"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2002.00122","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00122","pdf_url":"https://arxiv.org/pdf/2002.00122","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.00122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013650472","display_name":"Aparna Khare","orcid":"https://orcid.org/0000-0001-7151-3055","observed_orcids":["https://orcid.org/0000-0001-7151-3055"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khare, Aparna","raw_affiliation_strings":["Sunnyvale , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sunnyvale , CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sundaram, Shiva","raw_affiliation_strings":["Sunnyvale , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sunnyvale , CA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060740546","display_name":"Minhua Wu","orcid":"https://orcid.org/0000-0001-9798-2984","observed_orcids":["https://orcid.org/0000-0001-9798-2984"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Minhua","raw_affiliation_strings":["Sunnyvale , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sunnyvale , CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9688000082969666,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.031199999153614044,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7440000176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7431920170783997},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6243935227394104},{"id":"https://openalex.org/C57667952","wikidata":"https://www.wikidata.org/wiki/Q1154443","display_name":"Variable bitrate","level":3,"score":0.6065646409988403},{"id":"https://openalex.org/C34339180","wikidata":"https://www.wikidata.org/wiki/Q1325924","display_name":"Constant bitrate","level":4,"score":0.5290312767028809},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.526694655418396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5212531685829163},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.47430968284606934},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.44635096192359924},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.27265995740890503},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26625537872314453},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1701284945011139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13529211282730103},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2002.00122","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00122","pdf_url":"https://arxiv.org/pdf/2002.00122","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2002.00122","doi":"https://doi.org/10.48550/arxiv.2002.00122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.00122","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.00122","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00122","pdf_url":"https://arxiv.org/pdf/2002.00122","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.44999998807907104}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W312286380","https://openalex.org/W1538160025","https://openalex.org/W1575718033","https://openalex.org/W1885680957","https://openalex.org/W2014327836","https://openalex.org/W2057035781","https://openalex.org/W2117292163","https://openalex.org/W2131342762","https://openalex.org/W2530607852","https://openalex.org/W2589857635","https://openalex.org/W2621148391","https://openalex.org/W2746902340","https://openalex.org/W2886246524","https://openalex.org/W2900092534","https://openalex.org/W2921214093","https://openalex.org/W2921496354","https://openalex.org/W2940111934","https://openalex.org/W2957895207","https://openalex.org/W3215191595"],"related_works":["https://openalex.org/W2097846364","https://openalex.org/W2114244888","https://openalex.org/W4386172477","https://openalex.org/W1687620409","https://openalex.org/W3174162042","https://openalex.org/W2359580318","https://openalex.org/W4367694084","https://openalex.org/W2902391434","https://openalex.org/W2028638928","https://openalex.org/W2541582778"],"abstract_inverted_index":{"Recent":[0],"literature":[1],"has":[2],"shown":[3],"that":[4,63,79,101,152],"a":[5,54,85,90,116,172],"learned":[6],"front":[7],"end":[8],"with":[9,37,70,115,128],"multi-channel":[10,31,86],"audio":[11,58,87,93],"input":[12,88,94],"can":[13,112,168],"outperform":[14],"traditional":[15],"beam-forming":[16],"algorithms":[17],"for":[18,40,102],"automatic":[19],"speech":[20],"recognition":[21],"(ASR).":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"present":[27],"our":[28],"study":[29],"on":[30,158],"acoustic":[32,156],"modeling":[33],"using":[34,171],"OPUS":[35],"compression":[36],"different":[38,42],"bitrates":[39,134],"the":[41,46,57,64,103,109,125,129,142,146,155,166],"channels.":[43,148],"We":[44,77,149],"analyze":[45],"degradation":[47,167],"in":[48],"word":[49],"error":[50],"rate":[51],"(WER)":[52],"as":[53,72],"function":[55],"of":[56,108,165],"encoding":[59],"bitrate":[60,117,131,143,160],"and":[61],"show":[62,78,100,151],"WER":[65],"degrades":[66],"by":[67,153],"12.6%":[68],"relative":[69],"16kpbs":[71],"compared":[73],"to":[74,83,123,140,163],"uncompressed":[75],"audio.":[76],"its":[80,121,138],"always":[81],"preferable":[82,139],"have":[84],"over":[89],"single":[91,173],"channel":[92,127],"given":[95],"limited":[96],"bandwidth.":[97],"Our":[98],"results":[99],"best":[104],"WER,":[105],"when":[106],"one":[107],"two":[110,147],"channels":[111],"be":[113,169],"encoded":[114],"higher":[118],"than":[119,136],"32kbps,":[120],"optimal":[122],"encode":[124],"other":[126],"highest":[130],"possible.":[132],"For":[133],"lower":[135],"that,":[137],"distribute":[141],"equally":[144],"between":[145],"further":[150],"training":[154],"model":[157],"mixed":[159],"input,":[161],"up":[162],"50%":[164],"recovered":[170],"model.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}